Separate audio into individual stems with Demucs to isolate vocals, drums, bass, and other instruments for remixing, transcription, or editing workflows.
Separate audio into stems using Demucs.
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | htdemucs | |
| stems | No | ||
| overwrite | No | Explicitly allow replacing existing media. Existing non-media files are protected. | |
| input_path | Yes | ||
| output_dir | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.16.4Input schema / properties / overwriteAdded value: +{
+ "default": false,
+ "description": "Explicitly allow replacing existing media. Existing non-media files are protected.",
+ "title": "Overwrite",
+ "type": "boolean"
+}v1.16.0Input schema / additionalPropertiesAdded value: +falsev1.5.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure, but it only says what operation is performed. It does not explain that files are written to output_dir, how overwriting works beyond the schema's overwrite field, what stems are produced, or any compute or permission considerations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence with no filler or redundancy. It is appropriately sized for its content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values need not be described, but the description is still too thin for a five-parameter tool with low schema coverage and no annotations. An agent would not know how stems are selected, what model values are valid, or how output files are organized.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is only 20%, with just the overwrite parameter documented in the schema. The description does not clarify input_path, output_dir, valid model values, or what the stems parameter expects, beyond implying Demucs is the default model. It provides minimal compensation for the low schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb and resource: 'Separate audio into stems,' and names the Demucs backend. It is distinguishable from siblings like video_extract_audio or video_normalize_audio, though it does not explicitly name alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus related audio tools such as video_extract_audio, video_normalize_audio, or video_mix_audio. The description gives no context on prerequisites, intended use cases, or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.